May 2026

Example 1: The Viking 1 lander In the 1970s, NASA sent a pair of probes to Mars, the Viking 1 and Viking 2 missions. Total cost of $1B (1970), equivalent to about $7B (2025). The Viking 1 probe operated on Mars’s surface for six years, before its battery began to seriously degrade. One might have thought a battery problem like that would spell the irrevocable end of the mission. The probe had already launched and was now on […]

Ver mais

Release: datasette-llm-limits 0.1a0 This plugin works in conjunction with datasette-llm and datasette-llm-accountant to let you configure a per-user (or global) spending limit for LLM usage inside of Datasette. Configuration looks something like this: plugins: datasette-llm-limits: limits: per-user-daily: scope: actor window: rolling-24h amount_usd: 1.00 Tags: llm, datasette

Ver mais

Pre-training large language models is expensive enough that even modest efficiency improvements can translate into meaningful cost and time savings. Nous Research is releasing Token Superposition Training (TST), a method that substantially reduces pre-training wall-clock time at fixed compute without touching the model architecture, optimizer, tokenizer, parallelism strategy, or training data. At the 10B-A1B mixture-of-experts scale, TST reaches a lower final training loss than a matched-FLOPs baseline while consuming 4,768 B200-GPU-hours versus the baseline’s 12,311 — roughly a […]

Ver mais

Cline became ‘agentic’ before it was cool, but building on the bleeding edge usually leads to some structural debt. Over time, the agent loop and the VS Code extension became a package deal—making it a headache to maintain or move to new environments. Its tough to just keep layering features on a rigid core. Cline, the open-source AI coding agent used by millions of developers, shipped a significant architectural change this week: it extracted its internal agent harness […]

Ver mais

In this tutorial, we delve into CuPy as a powerful GPU-accelerated alternative to NumPy for high-performance numerical computing in Python. We start by inspecting the available CUDA device, checking the CuPy version, runtime details, GPU memory, and compute capability so that we understand the hardware environment before running heavy computations. Then, we compare NumPy and CuPy on large matrix multiplication and FFT workloads to see how GPU acceleration changes execution speed. Also, we work with memory pools, custom […]

Ver mais

This Mitchell Hashimoto quote about Bun migrating from Zig to Rust reminded me of a similar conversation I had at a conference last week. I was talking to someone who worked for a medium sized technology company with a pair of legacy/legendary iPhone and Android apps. They told me they had just completed a coding-agent driven rewrite of both apps to React Native. I asked why they chose that, given that coding agents presumably drive down the cost […]

Ver mais

[…] On the interesting side is how fungible programming languages are nowadays. Programming languages used to be LOCK IN, and they’re increasingly not so. You think the Bun rewrite in Rust is good for Rust? Bun has shown they can be in probably any language they want in roughly a week or two. Rust is expendable. Its useful until its not then it can be thrown out. That’s interesting! — Mitchell Hashimoto, on Bun porting from Zig to […]

Ver mais

I’ve been reading more about training in imagined environments, especially the work of the Dreamer series and RialTo, and I’m curious about how this could apply to CL. Take an example of a robot deployed in a home that notices it has a high failure rate when picking up a specific object (let’s say cans in a kitchen). It then builds a world model of the kitchen from it’s deployment data, generates can-grasping rollouts within it and RL […]

Ver mais